© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 838
    Prev
    Next
    INDEX
    Explanations

    Wikipedia-style encyclopedia article text with formal factual content.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jrosseruk
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĺ¯ä¸įæĺ¯
    -0.10
    åľ¨ä¸ĬéĿ¢
    -0.09
     basically
    -0.09
    ä¸ĬéĿ¢
    -0.09
     somebody
    -0.08
    æľīæŶåĢĻ
    -0.08
     everybody
    -0.08
    ä»Ģä¹ĪçļĦ
    -0.08
    ä¸Ģä¸ĭ
    -0.08
    çļĦéĤ£äºĽ
    -0.08
    POSITIVE LOGITS
    нга
    0.08
     foundational
    0.08
     despite
    0.08
    éģĹæĨ¾çļĦæĺ¯
    0.08
    æľ¬å¸ĸ
    0.08
    åį³åı¯å®ĮæĪIJ
    0.08
    åĿĩæĿ¥èĩª
    0.07
     Despite
    0.07
    éĹ»è¨Ģ
    0.07
    说罢
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.